1 / 89

Network Traffic Modeling

Network Traffic Modeling. Mark Crovella Boston University Computer Science. Outline of Day. 9:00 – 10:45 Lecture 1, including break 10:45 – 12:00 Exercise Set 1 12:00 – 13:30 Lunch 13:30 – 15:15 Lecture 2, including break 15:15 – 17:00 Exercise Set 2. The Big Picture.

Download Presentation

Network Traffic Modeling

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Network Traffic Modeling Mark Crovella Boston University Computer Science

  2. Outline of Day • 9:00 – 10:45 Lecture 1, including break • 10:45 – 12:00 Exercise Set 1 • 12:00 – 13:30 Lunch • 13:30 – 15:15 Lecture 2, including break • 15:15 – 17:00 Exercise Set 2

  3. The Big Picture • There are two main uses for Traffic Modeling: • Performance Analysis • Concerned with questions such as delay, throughput, packet loss. • Network Engineering and Management: • Concerned with questions such as capacity planning, traffic engineering, anomaly detection. • Some principal differences are that of timescale and stationarity.

  4. Relevant Timescales • Performance effects happen on short timescales • from nanoseconds up to an hour • Network Engineering effects happen on long timescales • from an hour to months 1 usec 1 sec 1 hour 1 day 1 week

  5. Stationarity, informally • “A stationary process has the property that the mean, variance and autocorrelation structure do not change over time.” • Informally: “we mean a flat looking series, without trend, constant variance over time, a constant autocorrelation structure over time and no periodic fluctuations (seasonality).” NIST/SEMATECH e-Handbook of Statistical Methods http://www.itl.nist.gov/div898/handbook/

  6. The 1-Hour / Stationarity Connection • Nonstationarity in traffic is primarily a result of varying human behavior over time • The biggest trend is diurnal • This trend can usually be ignored up to timescales of about an hour, especially in the “busy hour”

  7. Outline • Morning: Performance Evaluation • Part 0: Stationary assumption • Part 1: Models of fine-timescale behavior • Part 2: Traffic patterns seen in practice • Afternoon: Network Engineering • Models of long-timescale behavior • Part 1: Single Link • Part 2: Multiple Links

  8. Morning Part 1:Traffic Models for Performance Evaluation • Goal: Develop models useful for • Queueing analysis • eg, G/G/1 queues • Other analysis • eg, traffic shaping • Simulation • eg, router or network simulation

  9. A Reasonable Approach • Fully characterizing a stochastic process can be impossible • Potentially infinite set of properties to capture • Some properties can be very hard to estimate • A reasonable approach is to concentrate on two particular properties: marginal distribution and autocorrelation

  10. Marginals and Autocorrelation Characterizing a process in terms of these two properties gives you • a good approximate understanding of the process, • without involving a lot of work, • or requiring complicated models, • or requiring estimation of too many parameters. … Hopefully!

  11. Marginals Given a stochastic process X={Xi}, we are interested in the distribution of any Xi: i.e., f(x) = P(Xi=x) Since we assume X is stationary, it doesn’t matter which Xi we pick. Estimated using a histogram:

  12. Histograms and CDFs • A Histogram is often a poor estimate of the pdf f(x) because it involves binning the data • The CDF F(x) = P[Xi <= x] will have a point for each distinct data value; can be much more accurate

  13. Modeling the Marginals • We can form a compact summary of a pdf f(x) if we find that it is well described by a standard distribution – eg • Gaussian (Normal) • Exponential • Poisson • Pareto • Etc • Statistical methods exist for • asking whether a dataset is well described by a particular distribution • Estimating the relevant parameters

  14. Distributional Tails • A particularly important part of a distribution is the (upper) tail • P[X>x] • Large values dominate statistics and performance • “Shape” of tail critically important

  15. Light Tails, Heavy Tails • Light – Exponential or faster decline • Heavy – Slower than any exponential f1(x) = 2 exp(-2(x-1)) f2(x) = x-2

  16. Examining Tails • Best done using log-log complementary CDFs • Plot log(1-F(x)) vs log(x) 1-F2(x) 1-F1(x)

  17. Heavy Tails Arrive pre-1985: Scattered measurements note high variability in computer systems workloads 1985 – 1992: Detailed measurements note “long” distributional tails • File sizes • Process lifetimes 1993 – 1998: Attention focuses specifically on (approximately) polynomial tail shape: “heavy tails” post-1998: Heavy tails used in standard models

  18. Power Tails, Mathematically We say that a random variable X is power tailed if: where a ~ b means Focusing on polynomial shape allows Parsimonious description Capture of variability inaparameter

  19. A Fundamental Shift in Viewpoint • Traditional modeling methods have focused on distributions with “light” tails • Tails that decline exponentially fast (or faster) • Arbitrarily large observations are vanishingly rare • Heavy tailed models behave quite differently • Arbitrarily large observations have non-negligible probability • Large observations, although rare, can dominate a system’s performance characteristics

  20. Heavy Tails are Surprisingly Common • Sizes of data objects in computer systems • Files stored on Web servers • Data objects/flow lengths traveling through the Internet • Files stored in general-purpose Unix filesystems • I/O traces of filesystem, disk, and tape activity • Process/Job lifetimes • Node degree in certain graphs • Inter-domain and router structure of the Internet • Connectivity of WWW pages • Zipf’s Law

  21. Evidence: Web File Sizes Barford et al., World Wide Web, 1999

  22. Evidence: Process Lifetimes Harchol-Balter and Downey, ACM TOCS, 1997

  23. The Bad News • Workload metrics following heavy tailed distributions are extremely variable • For example, for power tails: • When a  2, distribution has infinite variance • When a 1, distribution has infinite mean • In practice, empirical moments are slow to converge – or nonconvergent • To characterize system performance, either: • Attention must shift to distribution itself, or • Attention must be paid to timescale of analysis

  24. Heavy Tails in Practice Power tailswith a=0.8 Large observations dominate statistics (e.g., sample mean)

  25. Autocorrelation • Once we have characterized the marginals, we know a lot about the process. • In fact, if the process consisted of i.i.d. samples, we would be done. • However, most traffic has the property that its measurements are not independent. • Lack of independence usually results in autocorrelation • Autocorrelation is the tendency for two measurements to both be greater than, or less than, the mean at the same time.

  26. Autocorrelation

  27. Measuring Autocorrelation Autocorrelation Function (ACF) (assumes stationarity): R(k) = Cov(Xn,Xn+k) = E[Xn Xn+k] – E2[X0]

  28. ACF of i.i.d. samples

  29. How Does Autocorrelation Arise? Network traffic is the superposition of flows Request Server Client Internet (TCP/IP) “click” Response

  30. Why Flows?: Sources appear to be ON/OFF ON OFF { { P1: P2: P3: • • •

  31. Superposition of ON/OFF sources  Autocorrelation P1: P2: P3:

  32. Morning Part 2: Traffic Patterns Seen in Practice Traffic patterns on a link are strongly affected by two factors: • amount of multiplexing on the link • Essentially – how many flows are sharing the link? • Where flows are bottlenecked • Is each flow’s bottleneck on, or off the link? • Do all bottlenecks have similar rate?

  33. Low Multiplexed Traffic • Marginals: highly variable • Autocorrelation: low

  34. Highly MultiplexedTraffic

  35. High Multiplexed, Bottlenecked Traffic • Marginals: tending to Gaussian • Autocorrelation: high

  36. Highly Mutiplexed, Mixed-Bottlenecks dec-pkt-1 (Internet Traffic Archive)

  37. Alpha and Beta Traffic • ON/OFF model revisited: High variability in connection rates (RTTs) Low rate = beta High rate = alpha + + + = = stableLevy noise fractionalGaussian noise Rice U., SPIN Group

  38. Long Range Dependence R[k] ~ a-k a > 1 R[k] ~ k-a 0 < a < 1 H=1-a/2

  39. Correlation and Scaling • Long range dependence affects how variability scales with timescale • Take a traffic timeseries Xn, sum it over blocks of size m • This is equivalent to observing the original process on a longer timescale • How do the mean and std dev change? • Mean will always grow in proportion to m • For i.i.d. data, the std dev will grow in proportion to sqrt(m) • So, for i.i.d. data, the process is “smoother” at longer timescale

  40. Self-similarity: unusual scaling of variability • Exact self-similarity of a zero-mean, stationary process Xn • H: Hurst parameter 1/2 < H < 1 • H = 1/2 for i.i.d. Xn • LRD leads to (at least) asymptotic s.s.

  41. Self Similarity in Practice H=0.95 H=0.50 10ms 1s 100s

  42. The Great Wave (Hokusai)

  43. How Does Self-Similarity Arise? Self-similarity  Autocorrelation  Flows Autocorrelation declines like a power law  Distribution of flow lengths has power law tail 

  44. Power Tailed ON/OFF sources Self-Similarity { { ON OFF P1: P2: P3:

  45. Measuring Scaling Properties • In principle, one can simply aggregate Xn over varying sizes of m, and plot resulting variance as a function of m • Linear behavior on a log-log plot gives an estimate of H (or a). • Slope > -1 indicates LRD WARNING: this method is very sensitive to violation of assumptions!

  46. Better: Wavelet-based estimation Veitch and Abry

  47. Optional Material: PerformanceImplications of Self-Similarity

  48. Performance implications of S.S. • Asymptotic queue length distribution (G/G/1) • For SRD Traffic: • For LRD Traffic: • Severe - but, realistic?

  49. Evaluating Self-Similarity • Queueing Models like these are open systems • delay does not feed back to source • TCP dynamics are not being considered • packet losses cause TCP to slow down • Better approach: • Closed network, detailed modeling of TCP dynamics • self-similarity traffic generated “naturally”

  50. Simulating Self-Similar Traffic • Simulated network with multiple clients, servers • Clients alternative between requests, idle times • Files drawn from heavy-tailed distribution • Vary a to vary self-similarity of traffic • Each request is simulated at packet level, including detailed TCP flow control • Compare with UDP (no flow control) as an example of an open system

More Related